© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14125
    Prev
    Next
    INDEX
    Explanations

    elements of Java programming language, particularly focusing on class definitions and variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets, often with HTML or console commands

    np_acts-logits-general · gemini-2.0-flash

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.73
     متعلقه
    -0.63
    InjectAttribute
    -0.60
     AssemblyCulture
    -0.59
     <<<<<<<<<<<<<<
    -0.56
    WriteTagHelper
    -0.55
     resourceCulture
    -0.54
    IsMutable
    -0.53
    XmlAccessType
    -0.53
     JADX
    -0.52
    POSITIVE LOGITS
     accuracy
    0.40
    lapia
    0.38
     comfort
    0.38
     whip
    0.38
     cherry
    0.37
    Invariant
    0.36
     opp
    0.36
    рта
    0.35
     Byron
    0.35
     hack
    0.35
    Activations Density 0.273%

    No Known Activations